Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

System and method for improving failure detection using collective intelligence with end-user feedback

a technology of collective intelligence and failure detection, applied in the direction of digital output to print units, instruments, nuclear elements, etc., can solve the problems of paper jam, device based on sensor devices cannot guarantee that all incidents will be detected correctly, and the probabilistic approach to examining printer usage pattern changes cannot guarantee a perfect accuracy, etc., to facilitate overcoming and distinguishing

Inactive Publication Date: 2012-03-27
XEROX CORP
View PDF16 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent describes a system and method for detecting device failures in a network and continuously updating a soft-failure detection algorithm based on user feedback. The system stores historical data and executes an algorithm to compute the probability of a device being in a failure state, which is then updated based on user feedback. The system can detect both hard and soft failures and can solicit and receive user feedback related to device status. The technical effect of this patent is to provide a more accurate and efficient way to detect and troubleshoot device failures in a network.

Problems solved by technology

When using an automatic failure detection system in a print infrastructure, a probabilistic approach examining printer usage pattern changes cannot guarantee a perfect accuracy.
An existing approach of monitoring devices based on sensor devices does not guarantee that all incidents will be detected correctly.
One example is the occurrence of repetitive paper jams: the printer does not work properly, but the printer system declares that it is working properly once the jam has been removed.
Conventional systems cannot solicit or employ user's feedback, but rather rely on hardware to warn a network administrator about potential failures.
For instance, a large number of users who switch between a first device (e.g., a first printer) and a second device (e.g., a second printer) can thereby overload the second device and cause the network to report a failure condition at the second device.
In another scenario, false alarms or fault conditions may be reported when a small number of users change their device usage due to a precise print resource need (e.g., color printing, large format, etc.), causing the network to report a false failure.
Conventional systems are subject to errors and imperfect decisions due to the generative nature of their algorithms, which make use of “priors” (e.g., historical usage information and / or patterns) that may not be applicable for all users and / or all situations.
The capabilities of such monitoring systems are basically limited by two aspects: available sensor data and its quality, and capability of the device embedded rules to explain failure states based on the limited sensor data.
Current embedded device monitoring systems suffer from weaknesses in both aspects.
Typically, quality image problems are not detectable by the internal monitoring systems of the device due to the unavailability of image quality sensors (e.g., a camera) in the device's output.
Adding new sensors to increase the monitoring capabilities of devices is only possible in high-end production devices, while in office devices where sales margins need to remain high while products stay competitive there is little possibility of adding new sensors.
Embedded diagnosis rule based systems are also limited not only by the data but also by the inherent limitations of rules systems.
With rule-based systems, it is difficult to target complex failure patterns.
For example, it is difficult to define the conditions of failures when complex temporal dependencies are involved.
Writing rules with some degree of uncertainty or variability in the way the failure can be inferred from sensor data is in general difficult to express using simple rules.
While the embedded diagnosis systems are slowly evolving, users are still suffering from device failures that are difficult to characterize, making devices unavailable and not always identified as unavailable from the device's sensor data.
This results in users collectively switching from one device to another without having the user making a specific failure report to the IT administrator in most cases.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for improving failure detection using collective intelligence with end-user feedback
  • System and method for improving failure detection using collective intelligence with end-user feedback
  • System and method for improving failure detection using collective intelligence with end-user feedback

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022]In accordance with various features described herein, systems and methods are described that facilitate using end-user feedback in order to automatically send users a request for details about a potential failure based on a detected change in their usage behavior, and adjust and tune the system so that the generative algorithm used in the soft failure detection (SFD) system gains specific knowledge of the environment and therefore becomes progressively more accurate. These aspects facilitate establishing a better link with the end user and improve the perceived level of quality of service while allowing the customer or user to selectively disable the feedback queries for input at any time.

[0023]With reference to FIG. 1, an SFD system 10 is illustrated that facilitates usage pattern analysis for device fleet monitoring by modeling and detecting changes in usage behaviors. The system improves the quality of service provided to users, which improves user satisfaction. “Soft” fail...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Systems and methods are described that facilitate using end-user feedback to automatically distinguish between a normal behavior and a device failure which can be a hard failure (e.g., a device malfunction) or a soft failure. For instance, upon detection of a usage switch from a first device to a second device by a user, a survey message is sent to the user to solicit information regarding the reasons for the switch. If the switch was triggered by a device malfunction, the detected device failure is verified and an alert is sent to an administrator and / or potentially impacted users. If the switch was triggered by the user's need for functionality (e.g., color printing, collation, etc.) not provided by the first device, which is otherwise functioning properly, then the detected failure is determined to be a failure and the failure detection algorithm is updated accordingly.

Description

BACKGROUND[0001]The subject application relates to failure detection in device networks. While the systems and methods described herein relate to distinguishing between hard and soft failures in device networks such as printing networks and the like, it will be appreciated that the described techniques may find application in other network systems, other failure detection applications, etc.[0002]When using an automatic failure detection system in a print infrastructure, a probabilistic approach examining printer usage pattern changes cannot guarantee a perfect accuracy. An existing approach of monitoring devices based on sensor devices does not guarantee that all incidents will be detected correctly. One example is the occurrence of repetitive paper jams: the printer does not work properly, but the printer system declares that it is working properly once the jam has been removed. In contrast, the users know in this case that the printer will fail to print the next paper. Conventiona...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(United States)
IPC IPC(8): G03G15/00G03G21/00
CPCG03G15/5079G06F11/0751G06F11/3476G06F11/0733G03G2215/00109G03G2221/1675
Inventor BOUCHARD, GUILLAUMECIRIZA, VICTORDONINI, LAURENTVALOBRA, PASCAL
Owner XEROX CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products